A Decision-Based Dynamic Ensemble Selection Method for Concept Drift

TL;DR

This paper introduces a novel online ensemble selection method that improves concept drift detection by considering the decision space, leading to higher detection precision and fewer false alarms in data stream classification.

Contribution

It presents a new dynamic ensemble selection approach that accounts for the decision space, enhancing drift detection and classification performance in data streams.

Findings

Achieved highest detection precision in artificial datasets.

Recorded lowest false alarms compared to existing methods.

Outperformed baselines in real-world datasets.

Abstract

We propose an online method for concept driftdetection based on dynamic classifier ensemble selection. Theproposed method generates a pool of ensembles by promotingdiversity among classifier members and chooses expert ensemblesaccording to global prequential accuracy values. Unlike currentdynamic ensemble selection approaches that use only local knowl-edge to select the most competent ensemble for each instance,our method focuses on selection taking into account the decisionspace. Consequently, it is well adapted to the context of driftdetection in data stream problems. The results of the experimentsshow that the proposed method attained the highest detection pre-cision and the lowest number of false alarms, besides competitiveclassification accuracy rates, in artificial datasets representingdifferent types of drifts. Moreover, it outperformed baselines indifferent real-problem datasets in terms of classification accuracy.